{"id":"https://openalex.org/W3134777502","doi":"https://doi.org/10.1158/1557-3265.adi21-po-084","title":"Abstract PO-084: Automated detection of pancreatic ductal adenocarcinoma (PDAC) on CT scans using artificial intelligence (AI): Impact of inclusion of automated pancreas segmentation on the accuracy of 3D-convolutional neural network (CNN)","display_name":"Abstract PO-084: Automated detection of pancreatic ductal adenocarcinoma (PDAC) on CT scans using artificial intelligence (AI): Impact of inclusion of automated pancreas segmentation on the accuracy of 3D-convolutional neural network (CNN)","publication_year":2021,"publication_date":"2021-03-01","ids":{"openalex":"https://openalex.org/W3134777502","doi":"https://doi.org/10.1158/1557-3265.adi21-po-084","mag":"3134777502"},"language":"en","primary_location":{"id":"doi:10.1158/1557-3265.adi21-po-084","doi":"https://doi.org/10.1158/1557-3265.adi21-po-084","is_oa":false,"landing_page_url":"https://doi.org/10.1158/1557-3265.adi21-po-084","pdf_url":null,"source":{"id":"https://openalex.org/S183149254","display_name":"Clinical Cancer Research","issn_l":"1078-0432","issn":["1078-0432","1557-3265"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320273","host_organization_name":"American Association for Cancer Research","host_organization_lineage":["https://openalex.org/P4310320273"],"host_organization_lineage_names":["American Association for Cancer Research"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Clinical Cancer Research","raw_type":"journal-article"},"volume":null,"type":"conference-abstract","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025784076","display_name":"Anurima Patra","orcid":"https://orcid.org/0000-0002-0935-6279","observed_orcids":["https://orcid.org/0000-0002-0935-6279"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurima Patra","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053303391","display_name":"Panagiotis D. Korfiatis","orcid":"https://orcid.org/0000-0003-2516-1751","observed_orcids":["https://orcid.org/0000-0003-2516-1751"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Korfiatis Panagiotis","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079912505","display_name":"Garima Suman","orcid":"https://orcid.org/0000-0002-4875-3170","observed_orcids":["https://orcid.org/0000-0002-4875-3170"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Garima Suman","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039093342","display_name":"Ananya Panda","orcid":"https://orcid.org/0000-0003-0862-0741","observed_orcids":["https://orcid.org/0000-0003-0862-0741"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananya Panda","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089041959","display_name":"Sushil Kumar Garg","orcid":"https://orcid.org/0000-0002-8621-0214","observed_orcids":["https://orcid.org/0000-0002-8621-0214"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sushil Kumar Garg","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077068545","display_name":"Ajit Harishkumar Goenka","orcid":"https://orcid.org/0000-0002-7804-2695","observed_orcids":["https://orcid.org/0000-0002-7804-2695"]},"institutions":[{"id":"https://openalex.org/I1330342723","display_name":"Mayo Clinic","ror":"https://ror.org/02qp3tb03","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1330342723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajit Goenka","raw_affiliation_strings":["Mayo Clinic, Rochester, MN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mayo Clinic, Rochester, MN","institution_ids":["https://openalex.org/I1330342723"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1330342723"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"5_Supplement","first_page":"PO","last_page":"084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10862","display_name":"AI in cancer detection","score":0.9452999830245972,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12422","display_name":"Radiomics and Machine Learning in Medical Imaging","score":0.02019999921321869,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.019700000062584877,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pancreatic-ductal-adenocarcinoma","display_name":"pancreatic ductal adenocarcinoma","score":0.9990000128746033},{"id":"https://openalex.org/keywords/automated-tumor-detection","display_name":"automated tumor detection","score":0.8700000047683716},{"id":"https://openalex.org/keywords/computed-tomography","display_name":"computed tomography","score":0.6660000085830688},{"id":"https://openalex.org/keywords/3d-convolutional-neural-networks","display_name":"3D convolutional neural networks","score":0.9049999713897705},{"id":"https://openalex.org/keywords/pancreas-segmentation","display_name":"pancreas segmentation","score":0.9769999980926514},{"id":"https://openalex.org/keywords/tumor-segmentation","display_name":"tumor segmentation","score":0.7080000042915344},{"id":"https://openalex.org/keywords/early-cancer-detection","display_name":"early cancer detection","score":0.671999990940094},{"id":"https://openalex.org/keywords/small-pancreatic-tumors","display_name":"small pancreatic tumors","score":0.6710000038146973},{"id":"https://openalex.org/keywords/portal-venous-phase-ct","display_name":"portal venous phase CT","score":0.7630000114440918},{"id":"https://openalex.org/keywords/bounding-box-localization","display_name":"bounding box localization","score":0.5180000066757202},{"id":"https://openalex.org/keywords/inception-resnet","display_name":"Inception-ResNet","score":0.7570000290870667},{"id":"https://openalex.org/keywords/u-net","display_name":"U-Net","score":0.5519999861717224},{"id":"https://openalex.org/keywords/medical-image-classification","display_name":"medical image classification","score":0.3720000088214874},{"id":"https://openalex.org/keywords/false-negative-results","display_name":"false-negative results","score":0.5}],"concepts":[{"id":"https://openalex.org/C146357865","wikidata":"https://www.wikidata.org/wiki/Q1123245","display_name":"Stage (stratigraphy)","level":2,"score":0.7023319005966187},{"id":"https://openalex.org/C2778764654","wikidata":"https://www.wikidata.org/wiki/Q9618","display_name":"Pancreas","level":2,"score":0.676995575428009},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.5940582752227783},{"id":"https://openalex.org/C2780210213","wikidata":"https://www.wikidata.org/wiki/Q212961","display_name":"Pancreatic cancer","level":3,"score":0.5249053239822388},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5180816650390625},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.502921998500824},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4586266875267029},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.42070186138153076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4087717533111572},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3596568703651428},{"id":"https://openalex.org/C121608353","wikidata":"https://www.wikidata.org/wiki/Q12078","display_name":"Cancer","level":2,"score":0.31432509422302246},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.19826677441596985},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.06614011526107788},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1158/1557-3265.adi21-po-084","doi":"https://doi.org/10.1158/1557-3265.adi21-po-084","is_oa":false,"landing_page_url":"https://doi.org/10.1158/1557-3265.adi21-po-084","pdf_url":null,"source":{"id":"https://openalex.org/S183149254","display_name":"Clinical Cancer Research","issn_l":"1078-0432","issn":["1078-0432","1557-3265"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-b","doyens","jufo-3","ki-jl-3","medline","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320273","host_organization_name":"American Association for Cancer Research","host_organization_lineage":["https://openalex.org/P4310320273"],"host_organization_lineage_names":["American Association for Cancer Research"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Clinical Cancer Research","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.9922999739646912,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4386352158","https://openalex.org/W4362664222","https://openalex.org/W4386295956","https://openalex.org/W4415978963","https://openalex.org/W4378417891","https://openalex.org/W4412492172","https://openalex.org/W4391111146","https://openalex.org/W4221102821","https://openalex.org/W4389781081","https://openalex.org/W4417200530"],"abstract_inverted_index":{"Abstract":[0],"Purpose:":[1],"Around":[2],"30%":[3],"of":[4,23,41,54,62,64,70,93,108,134,223,244,252,261,276,294,326,370,420,433,456,471,497,510,512,519,527],"PDAC":[5,24,55,97,138,160,214,268,307,334,344,380,413,475],"less":[6],"than":[7,403],"2-cm":[8],"tend":[9],"to":[10,16,30,35,46,57,226,465],"go":[11],"undetected":[12],"on":[13,67,122,185,193,300,428,476,502,516,533],"CT":[14,194,478,503],"due":[15],"their":[17],"subtle":[18,472],"imaging":[19],"signatures.":[20],"Automated":[21,495],"detection":[22,40,53,470,496],"using":[25,129,417,505],"AI":[26],"represents":[27],"an":[28,202,249,434],"opportunity":[29],"augment":[31],"physician":[32],"expertise":[33],"and":[34,56,98,119,139,151,154,161,189,206,217,255,347,383,453,537],"improve":[36],"outcomes":[37],"through":[38,210,264],"early":[39],"PDAC.":[42,353,389],"Our":[43],"purpose":[44],"was":[45,104,183,313,358,394,400],"develop":[47],"a":[48,186,196,231,235,283,423],"3D-CNN":[49,409],"for":[50,148,169,230,282,355,391,397],"fully":[51],"automated":[52,253,418,436,513],"further":[58],"evaluate":[59],"the":[60,68,191,211,221,265,288,295,301,310,330,448,463,517,528],"impact":[61],"inclusion":[63,511],"pancreas":[65,103,118,144,192,212,237,254,266,363,421,430,437,514],"segmentation":[66,257,438,515],"accuracy":[69,416,518],"this":[71],"3D-CNN.":[72],"Methods:":[73],"A":[74,82,132,176,246,318,357,405,408],"Medical":[75],"Imaging":[76],"Data":[77],"Readiness":[78],"Scale":[79],"(MIDaR)":[80],"level":[81],"dataset":[83],"(portal":[84],"venous":[85],"phase":[86],"CTs,":[87],"slice":[88,209,263],"thickness":[89],"\u2264":[90],"3.75":[91],"mm)":[92],"466":[94],"treatment-na\u00efve":[95],"biopsy-proven":[96],"1994":[99],"subjects":[100],"with":[101,110,137,142,159,164,195,343,379,414,422,443],"normal":[102,143,165,270,346,350,382,386],"created":[105],"after":[106],"exclusion":[107],"CTs":[109,123,136,141,156,158,163,328,342,351,378,387],"suboptimal":[111],"image":[112],"quality":[113],"or":[114,473],"biliary":[115],"stents.":[116],"Volumetric":[117],"tumor":[120,256],"segmentations":[121],"were":[124,145,167,174,298],"done":[125],"by":[126,248],"two":[127,296],"radiologists":[128],"3D":[130],"Slicer.":[131],"total":[133],"370":[135,140],"randomly":[146],"selected":[147],"separate":[149,172,429],"training":[150],"validation":[152,452],"sets,":[153],"396":[155,327,371],"(96":[157],"300":[162],"pancreas)":[166],"utilized":[168,201,220],"testing.":[170],"Two":[171],"3D-CNNs":[173],"trained.":[175],"three-stage":[177],"bounding-box-only":[178],"model":[179,239,245,356,392,398,404],"(A):":[180],"stage":[181,199,218,224,242,251],"1":[182,243],"based":[184],"UNET-like":[187],"architecture":[188,205],"localized":[190],"bounding":[197,424],"box;":[198],"2":[200,225],"Inception":[203],"ResNet":[204],"classified":[207,322,339,366,375],"each":[208,262],"into":[213,267,333,459],"vs.":[215,269,335],"normal;":[216],"3":[219],"output":[222],"generate":[227],"final":[228,277],"classification":[229,260,278],"given":[232,284],"CT.":[233,285],"Conversely,":[234],"four-stage":[236],"segmentation-based":[238],"(B)":[240],"included":[241],"followed":[247],"additional":[250,435],"(stage":[258,271,280],"2),":[259],"3)":[272],"and,":[273],"finally,":[274],"generation":[275],"score":[279],"4)":[281],"Area":[286],"under":[287],"receiver":[289],"operating":[290],"characteristic":[291],"curve":[292],"(AUROC)":[293],"models":[297,458],"compared":[299],"test":[302,311,331],"set.":[303],"Results:":[304],"Mean":[305],"(SD)":[306],"diameter":[308],"in":[309,447,469],"set":[312,332],"1.1":[314],"(0.43)":[315],"cm.":[316],"Model":[317,360],"(three-stage":[319],"bounding-box-only)":[320],"correctly":[321,365],"305":[323],"(77%)":[324],"out":[325,369],"from":[329],"normal.":[336],"It":[337,373],"incorrectly":[338,374],"12/96":[340],"(12.5%)":[341],"as":[345,352,381,388],"79/300":[348],"(26%)":[349],"AUROC":[354,390,396],"0.85.":[359],"B":[361,393,399],"(four-stage":[362],"segmentation-based)":[364],"351":[367],"(88%)":[368],"CTs.":[372],"13/96":[376],"(13.5%)":[377],"32/300":[384],"(10.7%)":[385],"0.94.":[395],"significantly":[401],"higher":[402],"(p<0.005).":[406],"Conclusion:":[407],"can":[410],"detect":[411],"small":[412,474],"high":[415],"localization":[419],"box":[425],"without":[426],"relying":[427],"segmentation.":[431],"Inclusion":[432],"step":[439],"reduced":[440],"false":[441],"positives":[442],"consequent":[444],"incremental":[445],"gain":[446],"model\u2019s":[449],"accuracy.":[450],"Prospective":[451],"subsequent":[454],"integration":[455],"such":[457],"clinical":[460],"workflows":[461],"has":[462],"potential":[464],"reduce":[466],"inadvertent":[467],"errors":[468],"standard-of-care":[477],"scans.":[479],"Citation":[480],"Format:":[481],"Anurima":[482],"Patra,":[483],"Korfiatis":[484],"Panagiotis,":[485],"Garima":[486],"Suman,":[487],"Ananya":[488],"Panda,":[489],"Sushil":[490],"Kumar":[491],"Garg,":[492],"Ajit":[493],"Goenka.":[494],"pancreatic":[498],"ductal":[499],"adenocarcinoma":[500],"(PDAC)":[501],"scans":[504],"artificial":[506],"intelligence":[507],"(AI):":[508],"Impact":[509],"3D-convolutional":[520],"neural":[521],"network":[522],"(CNN)":[523],"[abstract].":[524],"In:":[525],"Proceedings":[526],"AACR":[529],"Virtual":[530],"Special":[531],"Conference":[532],"Artificial":[534],"Intelligence,":[535],"Diagnosis,":[536],"Imaging;":[538],"2021":[539],"Jan":[540],"13-14.":[541],"Philadelphia":[542],"(PA):":[543],"AACR;":[544],"Clin":[545],"Cancer":[546],"Res":[547],"2021;27(5_Suppl):Abstract":[548],"nr":[549],"PO-084.":[550]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2021-03-15T00:00:00"}